© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12975
    Prev
    Next
    INDEX
    Explanations

    official actions

    np_acts-logits-general · gemini-2.5-flash-lite

    programming class declarations and section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cuenta
    0.47
    pulumi
    0.44
    гут
    0.44
     организм
    0.44
     психи
    0.44
    要
    0.43
    䡋
    0.42
     pecho
    0.41
    울
    0.41
    ="@+
    0.41
    POSITIVE LOGITS
     énon
    0.47
     obiettivi
    0.43
     continuación
    0.41
     Conclusion
    0.40
     Extensions
    0.40
    सरण
    0.40
     معی
    0.40
     conclusion
    0.39
     Arbitration
    0.39
     ครับ
    0.39
    Activations Density 0.000%

    No Known Activations